Mangat Randomized Response Group Testing Theory
Adeniran Adefemi T. *
Department of Statistics, University of Ibadan, Ibadan, Nigeria.
Eyo Daniel E.
Department of Statistics, University of Ibadan, Ibadan, Nigeria.
*Author to whom correspondence should be addressed.
Abstract
This paper proposed a new Randomized Response Group Testing (RRGT) model that estimates proportion of people characterizing a sensitive variable under study. Simple random sampling with replacement, binomial probability distribution and maximum likelihood were used as randomization procedure, sampling model and estimation technique, respectively. The distributional properties (expectation and variance) of the proposed estimator, efficiency comparison of the model with some existing models, and numerical illustration of all the competing models were also explored. The study found that the developed model outperformed competing existing orthodox RRMs and earlier RRGT model in terms of efficiency, privacy protection and it is economically advantageous.
Keywords: Randomised response, group testing, binomial probability distribution, maximum likelihood